Project OverviewMy project is about investigating the association of machine learning derived sleep, sedentary behaviour and physical activity with health outcomes. To reach this objective, I apply epidemiological methods and reasoning on data from large-scale population-based cohorts. First StudyChronic low back pain is a prevalent and costly condition, and regular physical activity may reduce its risk. Walking is a common and accessible form of physical activity, but its association with the risk of chronic low back pain is unclear. The aim of this project is to investigate the association between volume and intensity of walking and risk of chronic low back pain. Second StudyChronic low back pain is a prevalent and costly condition, and regular physical activity may reduce its risk. Sleep, sedentary behaviour and physical activity are suspected to associate with the risk of chronic low back pain but are mostly studied in isolation. The aim of this project is to investigate the association between the balance of sleep, sedentary behaviour and physical activity and the risk of chronic low back pain. Third StudyPhysical activity is an established health factor associated with the risk of various diseases. However, evidence linking physical activity and the risk repeated prescription of medication is missing. The aim of this project is to investigate the association between physical activity and the risk of long-term medication prescription. Fourth StudySpatiotemporal gait parameters like walking speed are established predictors of ageing and mortality. Such measurements are mostly obtained from clinical tests. More recently, researchers started to derive step cadence from accelerometer devices to investigate its association with health. However, comparison of predictive ability of clinical versus device-based spatiotemporal gait parameters is missing. Therefore, the aim of this study is to compare the ability of clinical walking speed and free-living step cadence to predict future all-cause mortality. |